Auto white balance correction value calculation device, method, program, and image pickup device

A non-transitory recording medium in which an auto white balance correction value calculation program for causing a computer to execute the auto white balance correction value calculation is stored, the program comprising computer-executable instructions of:

• obtaining image data;
• calculating a normal AWB correction value, which is a first auto white balance (AWB) correction value, based on the obtained image data;
• identifying a face area from the image data;
• calculating a face AWB correction value, which is a second AWB correction value, based on the face area of the image data;
• extracting first feature data from the image data and extracting second feature data from image data in the face area;
• and
• selecting one of the face AWB correction value and the normal AWB correction value as a total AWB correction value based on whether the comparison result of the first feature data and the second feature data is equal to or greater than a predetermined threshold or less than the threshold.

An auto white balance correction value calculation device comprising:

• an image data input unit which inputs image data;
• a normal AWB correction value calculation unit which calculates a normal AWB correction value, which is a first auto white balance (AWB) correction value, based on the image data inputted in the image data input unit;
• a face area identification unit which identifies a face area from the image data;
• a face AWB correction value calculation unit which calculates a face AWB correction value, which is a second AWB correction value, based on the face area of the image data;
• a feature data extraction unit which extracts first feature data from the image data and extracts second feature data from the image data in the face area;
• and
• a total AWB correction value calculation unit which calculates a total AWB correction value to be one of the face AWB correction value and the normal AWB correction value based on whether the comparison result of the first feature data and the second feature data is equal to or greater than a predetermined threshold or less than the threshold.